skills/jscraik/agent-skills/slides/Gen Agent Trust Hub

slides

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes several system utilities including 'libreoffice', 'inkscape', 'ghostscript', 'magick', and 'fc-list' via 'subprocess.run' and 'spawnSync'. These calls are implemented using array-based arguments rather than shell strings, which is a best practice to prevent command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of .pptx and .pdf documents.
  • Ingestion points: Document data is read and parsed in 'scripts/render_slides.py', 'scripts/detect_font.py', and 'scripts/slides_test.py'.
  • Boundary markers: The skill does not explicitly instruct the agent to use boundary markers when handling text extracted from slides.
  • Capability inventory: The skill has the ability to write to the file system and execute external binaries for file conversion.
  • Sanitization: The implementation uses the 'defusedxml' library for all XML parsing operations, providing protection against XML External Entity (XXE) and billion laughs attacks from malicious documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:13 PM
Security Audit — agent-trust-hub — slides